
The author addresses the non-IID issue in federated learning by proposing FedGH, a method that mitigates local drifts through Gradient Harmonization. FedGH consistently enhances FL baselines across diverse benchmarks and scenarios with stronger heterogeneity.


coremsg

addressing-non-iid-issue-in-federated-learning-with-gradient-harmonization


Addressing Non-IID Issue in Federated Learning with Gradient Harmonization


title_rewrite


Non-IID issue in federated learning is addressed through Gradient Harmonization, improving performance across diverse scenarios.


gradient-harmonization-addressing-non-iid-issue-in-federated-learning


Gradient Harmonization: Addressing Non-IID Issue in Federated Learning
